Qatar Road Surface Classification from OSM and AI Predictions

HeiGIT's dataset provides detailed road surface information for Qatar, distinguishing paved from unpaved roads. It contains approximately 0.0472 million kilometers of roads mapped in OpenStreetMap, with AI-derived estimates classifying 30.1549% as paved and 32.6687% as unpaved. The data was last updated on March 2, 2026, and is augmented with deep learning predictions from Mapillary imagery.

Use Cases

• Transportation planning based on road surface type and length statistics.
• Infrastructure analysis using attributes like highway type, surface, and width.
• Climate emissions assessment leveraging the urban/rural classification of roads.
• GIS applications utilizing the geospatial road network data and OSM attributes.

Strengths

• Integrates multiple data sources: OpenStreetMap, AI predictions from Mapillary, and urban layers from GHSU and AFRICAPOLIS.
• Provides specific statistics on road coverage, including 0.0142 million km of paved roads and 0.0154 million km of unpaved roads.
• Includes AI-derived features like predicted surface class and binary labels for model training or validation.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• About 37.1764% of road surface information is missing in the underlying OSM data.

Provenance

Source

Heidelberg Institute for Geoinformation Technology (HeiGIT), based on OpenStreetMap.

Collection Method

Surface classification derived using a hybrid deep learning approach on Mapillary imagery, combined with OSM tags.

Time Range

Mean timestamp of predictions is provided via the DL_mean_timestamp attribute.

Freshness

Last updated 2026-03-02 17:12:29.001802; freshness should be verified.

Geography

Qatar.